Melanoma diagnostic performance of an expert dermatologist with reflectance confocal microscopy: a 5-year single-center retrospective analysis of 1,960 lesions

Background: The diagnostic accuracy of dermatologists improves with experience, particularly in noninvasive skin tumor evaluation. Reflectance confocal microscopy (RCM) further enhances diagnostic precision, but the performance achievable by a single expert RCM reader with long-term experience is not well defined. Objective: To assess the diagnostic performance of a single expert dermatologist (>10 years of RCM experience at study initiation) over a 5-year period using RCM for lesions suspicious for melanoma. Methods: This retrospective study included 2,150 lesions evaluated clinically and dermoscopically between 2016 and 2020 and referred for RCM. Diagnostic performance was assessed by number needed to excise (NNE), positive predictive value (PPV), benign-to-malignant ratio, and benign melanocytic-to-melanoma ratio. Results: Of the 2150 lesions suspicious for melanoma on clinical and dermoscopy evaluations, RCM reduced excisions to 888 (41.3%). Overall NNE was 3.3, PPV was 30.6%, the benign-to-malignant ratio was 2.3, and the benign melanocytic-to-melanoma ratio was 2.2. Limitations: NNE, sensitivity and specificity from dermoscopy and RCM reader learning curve are missing. Conclusions: A single expert RCM reader achieved consistently high diagnostic performance, with low NNE, relatively high PPV, and a favorable benign-to-malignant excision ratio, providing an expert reader benchmark for future AI evaluation.

Authors

Publication Details

Journal
Dermatology
Published
2026-11-21
DOI
https://doi.org/10.1159/drm/ackag036
Primary Topic
Cutaneous Melanoma Detection and Management
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Melanoma diagnostic performance of an expert dermatologist with reflectance confocal microscopy: a 5-year single-center retrospective analysis of 1,960 lesions

Shaniko Kaleci, Silvana Ciardo, Johanna Chester, Francesca Farnetani et al.
Dermatology
Cutaneous Melanoma Detection and Management
article

Melanoma diagnostic performance of an expert dermatologist with reflectance confocal microscopy: a 5-year single-center retrospective analysis of 1,960 lesions

Shaniko Kaleci, Silvana Ciardo, Johanna Chester, Francesca Farnetani, Antonio Alma, Nicholas Gulati, Seher Banu Farabi Atak
article en

Abstract

Background: The diagnostic accuracy of dermatologists improves with experience, particularly in noninvasive skin tumor evaluation. Reflectance confocal microscopy (RCM) further enhances diagnostic precision, but the performance achievable by a single expert RCM reader with long-term experience is not well defined. Objective: To assess the diagnostic performance of a single expert dermatologist (>10 years of RCM experience at study initiation) over a 5-year period using RCM for lesions suspicious for melanoma. Methods: This retrospective study included 2,150 lesions evaluated clinically and dermoscopically between 2016 and 2020 and referred for RCM. Diagnostic performance was assessed by number needed to excise (NNE), positive predictive value (PPV), benign-to-malignant ratio, and benign melanocytic-to-melanoma ratio. Results: Of the 2150 lesions suspicious for melanoma on clinical and dermoscopy evaluations, RCM reduced excisions to 888 (41.3%). Overall NNE was 3.3, PPV was 30.6%, the benign-to-malignant ratio was 2.3, and the benign melanocytic-to-melanoma ratio was 2.2. Limitations: NNE, sensitivity and specificity from dermoscopy and RCM reader learning curve are missing. Conclusions: A single expert RCM reader achieved consistently high diagnostic performance, with low NNE, relatively high PPV, and a favorable benign-to-malignant excision ratio, providing an expert reader benchmark for future AI evaluation.

Dermatology
Cutaneous Melanoma Detection and Management
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon